deps: update ICU to 68.1

Refs: https://github.com/unicode-org/icu/releases/tag/release-68-1

PR-URL: #36187
Reviewed-By: Richard Lau <[email protected]>
Reviewed-By: Gireesh Punathil <[email protected]>
Reviewed-By: Michael Dawson <[email protected]>
Reviewed-By: Rich Trott <[email protected]>
Reviewed-By: Jiawen Geng <[email protected]>

Author: targos

LICENSE

@@ -418,9 +418,9 @@ The externally maintained libraries used by Node.js are:
      #  Copyright (c) 2013 International Business Machines Corporation
      #  and others. All Rights Reserved.
      #
-     # Project: http://code.google.com/p/lao-dictionary/
-     # Dictionary: http://lao-dictionary.googlecode.com/git/Lao-Dictionary.txt
-     # License: http://lao-dictionary.googlecode.com/git/Lao-Dictionary-LICENSE.txt
+     # Project: https://github.com/veer66/lao-dictionary
+     # Dictionary: https://github.com/veer66/lao-dictionary/blob/master/Lao-Dictionary.txt
+     # License: https://github.com/veer66/lao-dictionary/blob/master/Lao-Dictionary-LICENSE.txt
      #              (copied below)
      #
      #  This file is derived from the above dictionary, with slight

deps/icu-small/LICENSE

@@ -284,9 +284,9 @@ property of their respective owners.
  #  Copyright (c) 2013 International Business Machines Corporation
  #  and others. All Rights Reserved.
  #
- # Project: http://code.google.com/p/lao-dictionary/
- # Dictionary: http://lao-dictionary.googlecode.com/git/Lao-Dictionary.txt
- # License: http://lao-dictionary.googlecode.com/git/Lao-Dictionary-LICENSE.txt
+ # Project: https://github.com/veer66/lao-dictionary
+ # Dictionary: https://github.com/veer66/lao-dictionary/blob/master/Lao-Dictionary.txt
+ # License: https://github.com/veer66/lao-dictionary/blob/master/Lao-Dictionary-LICENSE.txt
  #              (copied below)
  #
  #  This file is derived from the above dictionary, with slight

deps/icu-small/README-FULL-ICU.txt

@@ -1,8 +1,8 @@
 ICU sources - auto generated by shrink-icu-src.py
 
 This directory contains the ICU subset used by --with-intl=full-icu
-It is a strict subset of ICU 67 source files with the following exception(s):
-* deps/icu-small/source/data/in/icudt67l.dat.bz2 : compressed data file
+It is a strict subset of ICU 68 source files with the following exception(s):
+* deps/icu-small/source/data/in/icudt68l.dat.bz2 : compressed data file
 
 
 To rebuild this directory, see ../../tools/icu/README.md

deps/icu-small/source/.clang-format

@@ -0,0 +1,11 @@
+# © 2020 and later: Unicode, Inc. and others.
+# License & terms of use: http://www.unicode.org/copyright.html
+
+---
+Language: Cpp
+BasedOnStyle: LLVM
+IndentWidth: 4
+ColumnLimit: 105
+AllowShortBlocksOnASingleLine: false
+AllowShortIfStatementsOnASingleLine: true
+...

deps/icu-small/source/common/bmpset.h

@@ -101,7 +101,7 @@ class BMPSet : public UMemory {
      */
     UBool latin1Contains[0x100];
 
-    /* TRUE if contains(U+FFFD). */
+    /* true if contains(U+FFFD). */
     UBool containsFFFD;
 
     /*

deps/icu-small/source/common/brkeng.h

@@ -54,7 +54,7 @@ class LanguageBreakEngine : public UMemory {
   * a particular kind of break.</p>
   *
   * @param c A character which begins a run that the engine might handle
-  * @return TRUE if this engine handles the particular character and break
+  * @return true if this engine handles the particular character and break
   * type.
   */
   virtual UBool handles(UChar32 c) const = 0;
@@ -171,7 +171,7 @@ class UnhandledEngine : public LanguageBreakEngine {
   * a particular kind of break.</p>
   *
   * @param c A character which begins a run that the engine might handle
-  * @return TRUE if this engine handles the particular character and break
+  * @return true if this engine handles the particular character and break
   * type.
   */
   virtual UBool handles(UChar32 c) const;

deps/icu-small/source/common/bytesinkutil.h

@@ -45,9 +45,9 @@ class U_COMMON_API ByteSinkUtil {
     static UBool appendUnchanged(const uint8_t *s, int32_t length,
                                  ByteSink &sink, uint32_t options, Edits *edits,
                                  UErrorCode &errorCode) {
-        if (U_FAILURE(errorCode)) { return FALSE; }
+        if (U_FAILURE(errorCode)) { return false; }
         if (length > 0) { appendNonEmptyUnchanged(s, length, sink, options, edits); }
-        return TRUE;
+        return true;
     }
 
     static UBool appendUnchanged(const uint8_t *s, const uint8_t *limit,

deps/icu-small/source/common/charstr.cpp

@@ -20,6 +20,7 @@
 #include "cmemory.h"
 #include "cstring.h"
 #include "uinvchar.h"
+#include "ustr_imp.h"
 
 U_NAMESPACE_BEGIN
 
@@ -46,6 +47,19 @@ char *CharString::cloneData(UErrorCode &errorCode) const {
     return p;
 }
 
+int32_t CharString::extract(char *dest, int32_t capacity, UErrorCode &errorCode) const {
+    if (U_FAILURE(errorCode)) { return len; }
+    if (capacity < 0 || (capacity > 0 && dest == nullptr)) {
+        errorCode = U_ILLEGAL_ARGUMENT_ERROR;
+        return len;
+    }
+    const char *src = buffer.getAlias();
+    if (0 < len && len <= capacity && src != dest) {
+        uprv_memcpy(dest, src, len);
+    }
+    return u_terminateChars(dest, capacity, len, &errorCode);
+}
+
 CharString &CharString::copyFrom(const CharString &s, UErrorCode &errorCode) {
     if(U_SUCCESS(errorCode) && this!=&s && ensureCapacity(s.len+1, 0, errorCode)) {
         len=s.len;
@@ -197,7 +211,7 @@ CharString &CharString::appendPathPart(StringPiece s, UErrorCode &errorCode) {
     }
     char c;
     if(len>0 && (c=buffer[len-1])!=U_FILE_SEP_CHAR && c!=U_FILE_ALT_SEP_CHAR) {
-        append(U_FILE_SEP_CHAR, errorCode);
+        append(getDirSepChar(), errorCode);
     }
     append(s, errorCode);
     return *this;
@@ -207,9 +221,19 @@ CharString &CharString::ensureEndsWithFileSeparator(UErrorCode &errorCode) {
     char c;
     if(U_SUCCESS(errorCode) && len>0 &&
             (c=buffer[len-1])!=U_FILE_SEP_CHAR && c!=U_FILE_ALT_SEP_CHAR) {
-        append(U_FILE_SEP_CHAR, errorCode);
+        append(getDirSepChar(), errorCode);
     }
     return *this;
 }
 
+char CharString::getDirSepChar() const {
+    char dirSepChar = U_FILE_SEP_CHAR;
+#if (U_FILE_SEP_CHAR != U_FILE_ALT_SEP_CHAR)
+    // We may need to return a different directory separator when building for Cygwin or MSYS2.
+    if(len>0 && !uprv_strchr(data(), U_FILE_SEP_CHAR) && uprv_strchr(data(), U_FILE_ALT_SEP_CHAR))
+        dirSepChar = U_FILE_ALT_SEP_CHAR;
+#endif
+    return dirSepChar;
+}
+
 U_NAMESPACE_END

deps/icu-small/source/common/charstr.h

@@ -87,6 +87,22 @@ class U_COMMON_API CharString : public UMemory {
      * The caller must uprv_free() the result.
      */
     char *cloneData(UErrorCode &errorCode) const;
+    /**
+     * Copies the contents of the string into dest.
+     * Checks if there is enough space in dest, extracts the entire string if possible,
+     * and NUL-terminates dest if possible.
+     *
+     * If the string fits into dest but cannot be NUL-terminated (length()==capacity),
+     * then the error code is set to U_STRING_NOT_TERMINATED_WARNING.
+     * If the string itself does not fit into dest (length()>capacity),
+     * then the error code is set to U_BUFFER_OVERFLOW_ERROR.
+     *
+     * @param dest Destination string buffer.
+     * @param capacity Size of the dest buffer (number of chars).
+     * @param errorCode ICU error code.
+     * @return length()
+     */
+    int32_t extract(char *dest, int32_t capacity, UErrorCode &errorCode) const;
 
     bool operator==(StringPiece other) const {
         return len == other.length() && (len == 0 || uprv_memcmp(data(), other.data(), len) == 0);
@@ -141,13 +157,13 @@ class U_COMMON_API CharString : public UMemory {
 
     /**
      * Appends a filename/path part, e.g., a directory name.
-     * First appends a U_FILE_SEP_CHAR if necessary.
+     * First appends a U_FILE_SEP_CHAR or U_FILE_ALT_SEP_CHAR if necessary.
      * Does nothing if s is empty.
      */
     CharString &appendPathPart(StringPiece s, UErrorCode &errorCode);
 
     /**
-     * Appends a U_FILE_SEP_CHAR if this string is not empty
+     * Appends a U_FILE_SEP_CHAR or U_FILE_ALT_SEP_CHAR if this string is not empty
      * and does not already end with a U_FILE_SEP_CHAR or U_FILE_ALT_SEP_CHAR.
      */
     CharString &ensureEndsWithFileSeparator(UErrorCode &errorCode);
@@ -160,6 +176,12 @@ class U_COMMON_API CharString : public UMemory {
 
     CharString(const CharString &other); // forbid copying of this class
     CharString &operator=(const CharString &other); // forbid copying of this class
+
+    /**
+     * Returns U_FILE_ALT_SEP_CHAR if found in string, and U_FILE_SEP_CHAR is not found.
+     * Otherwise returns U_FILE_SEP_CHAR.
+     */
+    char getDirSepChar() const;
 };
 
 U_NAMESPACE_END

deps/icu-small/source/common/charstrmap.h

@@ -0,0 +1,55 @@
+// © 2020 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
+
+// charstrmap.h
+// created: 2020sep01 Frank Yung-Fong Tang
+
+#ifndef __CHARSTRMAP_H__
+#define __CHARSTRMAP_H__
+
+#include <utility>
+#include "unicode/utypes.h"
+#include "unicode/uobject.h"
+#include "uhash.h"
+
+U_NAMESPACE_BEGIN
+
+/**
+ * Map of const char * keys & values.
+ * Stores pointers as is: Does not own/copy/adopt/release strings.
+ */
+class CharStringMap final : public UMemory {
+public:
+    /** Constructs an unusable non-map. */
+    CharStringMap() : map(nullptr) {}
+    CharStringMap(int32_t size, UErrorCode &errorCode) {
+        map = uhash_openSize(uhash_hashChars, uhash_compareChars, uhash_compareChars,
+                             size, &errorCode);
+    }
+    CharStringMap(CharStringMap &&other) U_NOEXCEPT : map(other.map) {
+        other.map = nullptr;
+    }
+    CharStringMap(const CharStringMap &other) = delete;
+    ~CharStringMap() {
+        uhash_close(map);
+    }
+
+    CharStringMap &operator=(CharStringMap &&other) U_NOEXCEPT {
+        map = other.map;
+        other.map = nullptr;
+        return *this;
+    }
+    CharStringMap &operator=(const CharStringMap &other) = delete;
+
+    const char *get(const char *key) const { return static_cast<const char *>(uhash_get(map, key)); }
+    void put(const char *key, const char *value, UErrorCode &errorCode) {
+        uhash_put(map, const_cast<char *>(key), const_cast<char *>(value), &errorCode);
+    }
+
+private:
+    UHashtable *map;
+};
+
+U_NAMESPACE_END
+
+#endif  //  __CHARSTRMAP_H__